Westlake ENCODE Lab

university

https://westlake-encode-lab.github.io/

Activity Feed

AI & ML interests

Efficient AI, AI Evaluation, Computer Vision, Machine Learning System

Recent Activity

Huan-WhoRegisteredMyName authored a paper about 2 hours ago

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

YIGE24 submitted a paper about 7 hours ago

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

Huan-WhoRegisteredMyName submitted a paper about 7 hours ago

Universal Textual Teaching for LLMs

View all activity

Papers

SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

View all Papers

encodelab 's papers 6

Submitted by

Huan Wang

SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference

Westlake ENCODE Lab

Submitted by

Xueyi Chen

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

Westlake ENCODE Lab

3 1

Submitted by

Yihao Hu

SEAL: Synergistic Co-Evolution of Agents and Learning Environments

Westlake ENCODE Lab

Submitted by

Xin Jin

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Westlake ENCODE Lab

22 1

Submitted by

Sicheng Feng

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

Westlake ENCODE Lab

67 2

Submitted by

Song Wang

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Westlake ENCODE Lab

47 3

AI & ML interests

Recent Activity

Papers

Team members 1

SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

SEAL: Synergistic Co-Evolution of Agents and Learning Environments

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning